You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
To get access, please fill in the short form at https://saidzoda.com/access. We approve requests after we receive the form.
Log in or Sign Up to review the conditions and access this model content.
sl-saxaul
How to get access: please fill in the short form at saidzoda.com/access. We approve requests after we receive the form.
Gemma-4-E4B-it adapted to Tajik, Uzbek, Kazakh and Kyrgyz by Saidzoda AI Lab: CPT (1 epoch) -> SFT -> tool-calling SFT.
LoRA adapters only (apply in order: cpt/ -> sft/checkpoint-2500/ -> tool/).
sft/checkpoint-2500is the selected SFT checkpoint (best on both log-likelihood and chat-mode evals); 15000 / 17500 / 137032 (final) are kept for comparison.tool/was trained on top of CPT + SFT checkpoint-2500.records/holds the configs, code, loss logs and every eval file (seerecords/sft/eval/RANKING.md,records/sft/eval_chat/CHAT_RANKING.md).
Access is granted on request.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support